
import pandas as pd


A = pd.read_csv("/users/ranjeetgaikwad/desktop/data science class/Cars93.csv")


A.head()


A.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 93 entries, 0 to 92
Data columns (total 28 columns):
 #   Column              Non-Null Count  Dtype  
---  ------              --------------  -----  
 0   Unnamed: 0          93 non-null     int64  
 1   Manufacturer        93 non-null     object 
 2   Model               93 non-null     object 
 3   Type                93 non-null     object 
 4   Min.Price           93 non-null     float64
 5   Price               93 non-null     float64
 6   Max.Price           93 non-null     float64
 7   MPG.city            93 non-null     int64  
 8   MPG.highway         93 non-null     int64  
 9   AirBags             89 non-null     object 
 10  DriveTrain          93 non-null     object 
 11  Cylinders           93 non-null     object 
 12  EngineSize          93 non-null     float64
 13  Horsepower          93 non-null     int64  
 14  RPM                 93 non-null     int64  
 15  Rev.per.mile        93 non-null     int64  
 16  Man.trans.avail     93 non-null     object 
 17  Fuel.tank.capacity  93 non-null     float64
 18  Passengers          93 non-null     int64  
 19  Length              93 non-null     int64  
 20  Wheelbase           93 non-null     int64  
 21  Width               93 non-null     int64  
 22  Turn.circle         93 non-null     int64  
 23  Rear.seat.room      91 non-null     float64
 24  Luggage.room        82 non-null     float64
 25  Weight              93 non-null     int64  
 26  Origin              93 non-null     object 
 27  Make                93 non-null     object 
dtypes: float64(7), int64(12), object(9)
memory usage: 20.5+ KB


#Univariate Analysis

cat = []
con = []
for i in A.columns:
    if(A[i].dtypes == "object"):
        cat.append(i)
    else:
        con.append(i)


import matplotlib.pyplot as plt
import seaborn as sb


for i in A.columns:
    if(A[i].dtypes == "object"):
        sb.boxplot(A[i],A.Price) #Boxplot between categorical and continuous columns
        plt.xlabel(i)
        plt.ylabel('Price')
        plt.show()
    else:
        plt.scatter(A[i],A.Price) #Scatter plot between continuous and continuous columns
        plt.xlabel('Price')
        plt.ylabel(i)
        plt.show()

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

cat

['Manufacturer',
 'Model',
 'Type',
 'AirBags',
 'DriveTrain',
 'Cylinders',
 'Man.trans.avail',
 'Origin',
 'Make']

con

['Unnamed: 0',
 'Min.Price',
 'Price',
 'Max.Price',
 'MPG.city',
 'MPG.highway',
 'EngineSize',
 'Horsepower',
 'RPM',
 'Rev.per.mile',
 'Fuel.tank.capacity',
 'Passengers',
 'Length',
 'Wheelbase',
 'Width',
 'Turn.circle',
 'Rear.seat.room',
 'Luggage.room',
 'Weight']


import seaborn as sb
import matplotlib.pyplot as plt


for i in con:
    sb.distplot(A[i])
    plt.show()

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)


plt.figure(figsize=(40,19))
plt.subplot(3,3,1)
sb.distplot(A[['MPG.highway']])
plt.subplot(3,3,2)
sb.distplot(A.EngineSize)
plt.subplot(3,3,3)
sb.distplot(A.Horsepower)
plt.subplot(3,3,4)
sb.distplot(A[['Fuel.tank.capacity']])
plt.subplot(3,3,5)
sb.distplot(A.Weight)

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)
/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

<AxesSubplot:xlabel='Weight', ylabel='Density'>


A['Price'].hist()

<AxesSubplot:>


sb.countplot(A.AirBags)

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

<AxesSubplot:xlabel='AirBags', ylabel='count'>


sb.countplot(A.Cylinders)

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

<AxesSubplot:xlabel='Cylinders', ylabel='count'>


A["Type"].value_counts()

Midsize    22
Small      21
Compact    16
Sporty     14
Large      11
Van         9
Name: Type, dtype: int64


A["Type"].value_counts().plot(kind = "barh")

<AxesSubplot:>


A["Type"].value_counts().plot(kind = "bar")

<AxesSubplot:>


A["Type"].value_counts().plot(kind = "pie")

<AxesSubplot:ylabel='Type'>


# Bivariate
#con vs con

plt.scatter(A.Price, A.EngineSize, c = "black")
plt.xticks(range(0, 80, 5))
plt.yticks(range(0, 6, 1))
plt.xlabel("Price")
plt.ylabel("EngineSize")
plt.title("Price avs Engine Scatterplot")

Text(0.5, 1.0, 'Price avs Engine Scatterplot')


plt.scatter(A.Price, A.Horsepower, c = "red")

<matplotlib.collections.PathCollection at 0x7fd07e19d580>


# cat vs con

sb.boxplot(A.Cylinders, A.Price)

/opt/anaconda3/envs/deep_learning/lib/python3.8/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

<AxesSubplot:xlabel='Cylinders', ylabel='Price'>


#cat vs cat 

pd.crosstab(A.Model, A.Type)


#Multivariate Analysis

sb.pairplot(A)

<seaborn.axisgrid.PairGrid at 0x7fd07e659d30>


A.isna().sum()

Unnamed: 0             0
Manufacturer           0
Model                  0
Type                   0
Min.Price              0
Price                  0
Max.Price              0
MPG.city               0
MPG.highway            0
AirBags                4
DriveTrain             0
Cylinders              0
EngineSize             0
Horsepower             0
RPM                    0
Rev.per.mile           0
Man.trans.avail        0
Fuel.tank.capacity     0
Passengers             0
Length                 0
Wheelbase              0
Width                  0
Turn.circle            0
Rear.seat.room         2
Luggage.room          11
Weight                 0
Origin                 0
Make                   0
dtype: int64


B = pd.DataFrame(A.isna().sum(), columns=["missing_values"])


B[B.missing_values>0]


#function of fill the missing values

def replacer(df):
    Q = pd.DataFrame(df.isna().sum())
    Q.columns = ["CT"]
    w = list(Q[Q.CT>0].index)     #list of colummns with missing values
    
    cat = []                      #distinguishing between in categorical and continuous  
    con = []
    for i in w:
        if(df[i].dtypes == "object"):
            cat.append(i)
        else:
            con.append(i)
            
    for i in con:                 #filling in the missing values
        replacer = df[i].mean()
        df[i] = df[i].fillna(replacer)
        
    for i in cat:
        replacer = pd.DataFrame(df[i].value_counts()).index[0]
        df[i] = df[i].fillna(replacer)


replacer(A)


B = pd.DataFrame(A.isna().sum(), columns = ["check"])

B


sb.pairplot(A)

<seaborn.axisgrid.PairGrid at 0x7fd06c85e9d0>


A.isna().sum()

Unnamed: 0            0
Manufacturer          0
Model                 0
Type                  0
Min.Price             0
Price                 0
Max.Price             0
MPG.city              0
MPG.highway           0
AirBags               0
DriveTrain            0
Cylinders             0
EngineSize            0
Horsepower            0
RPM                   0
Rev.per.mile          0
Man.trans.avail       0
Fuel.tank.capacity    0
Passengers            0
Length                0
Wheelbase             0
Width                 0
Turn.circle           0
Rear.seat.room        0
Luggage.room          0
Weight                0
Origin                0
Make                  0
dtype: int64

	Unnamed: 0	Manufacturer	Model	Type	Min.Price	Price	Max.Price	MPG.city	MPG.highway	AirBags	...	Passengers	Length	Wheelbase	Width	Turn.circle	Rear.seat.room	Luggage.room	Weight	Origin	Make
0	1	Acura	Integra	Small	12.9	15.9	18.8	25	31	None	...	5	177	102	68	37	26.5	11.0	2705	non-USA	Acura Integra
1	2	Acura	Legend	Midsize	29.2	33.9	38.7	18	25	Driver & Passenger	...	5	195	115	71	38	30.0	15.0	3560	non-USA	Acura Legend
2	3	Audi	90	Compact	25.9	29.1	32.3	20	26	Driver only	...	5	180	102	67	37	28.0	14.0	3375	non-USA	Audi 90
3	4	Audi	100	Midsize	30.8	37.7	44.6	19	26	NaN	...	6	193	106	70	37	31.0	17.0	3405	non-USA	Audi 100
4	5	BMW	535i	Midsize	23.7	30.0	36.2	22	30	Driver only	...	4	186	109	69	39	27.0	13.0	3640	non-USA	BMW 535i

Type	Compact	Large	Midsize	Small	Sporty	Van
Model
100	0	0	1	0	0	0
190E	1	0	0	0	0	0
240	1	0	0	0	0	0
300E	0	0	1	0	0	0
323	0	0	0	1	0	0
...	...	...	...	...	...	...
Taurus	0	0	1	0	0	0
Tempo	1	0	0	0	0	0
Tercel	0	0	0	1	0	0
Town_Car	0	1	0	0	0	0
Vision	0	1	0	0	0	0

Exploratory Data Analysis(EDA)¶

Missing value Treatment¶